Information processing method, information processing apparatus, information processing program, method for generating trained model, trained model, and measurement device

Abstract

Provided are an information processing method, an information processing apparatus, and an information processing program that are capable of highly accurately determining the presence or absence of respiratory disease symptoms, a trained model used therein, a method for generating the same, and a measurement device.　A processor (11) performs processing for: acquiring data based on measurement data measured from a subject and indicating the subject's respiratory condition; acquiring medication history information and exercise history information regarding the subject's medication history and exercise history in a past period before the measurement timing of the measurement data; and inputting the data, the medication history information, and the exercise history information to a trained model and obtaining a determination result on the presence or absence of respiratory disease symptoms in the subject from the trained model.

Description

Information processing method, information processing device, information processing program, trained model generation method, trained model, and measuring device

[0001] The technology disclosed herein relates to an information processing method, an information processing device, an information processing program, a method for generating a trained model, a trained model, and a measuring instrument.

[0002] Patent Document 1 describes a treatment support device that includes a processor that acquires measurement sound data from a lung sound measuring device that measures lung sounds and is attached to the body of a subject, acquires behavioral data of the subject during the measurement period of the measurement sound data, and displays an image based on the measurement sound data and the behavioral data on a display device of an external device.

[0003] Patent Document 2 describes a treatment support device that includes a processor that acquires determination result data from a device that determines the airway condition of a subject during a lung sound measurement period based on lung sounds measured from the subject, and status information that indicates the condition of the subject during a period that is different from the measurement period but that is on a day that includes the measurement period, and records the determination result data and the status information in association with each other.

[0004] Japanese Patent Publication No. 2022-016972 Japanese Patent Publication No. 2021-194272

[0005] The presence or absence of symptoms of respiratory diseases such as asthma, pulmonary fibrosis, upper airway obstruction, or chronic obstructive pulmonary disease can be determined with high accuracy by a doctor directly examining the patient using a stethoscope or other device. Meanwhile, devices such as sensors and peak flow meters that can detect wheezing are also known, and the use of these devices makes it possible to determine the presence or absence of symptoms without a doctor's examination. The presence or absence of symptoms is determined using devices that measure the patient's respiratory sounds or lung capacity. However, because patients' physical conditions vary, it is desirable to determine the presence or absence of symptoms by taking their physical conditions into consideration.

[0006] The technology disclosed herein aims to provide an information processing method, information processing device, and information processing program that can accurately determine the presence or absence of symptoms of respiratory disease, as well as a trained model used therein and a method for generating the same, and a measuring device.

[0007] The technology of the present disclosure is as follows: Note that, although the corresponding components in the following embodiments are shown in parentheses, the present disclosure is not limited to these.

[0008] (1) An information processing method in which a processor (processor 11) acquires data (processed measurement data) based on measurement data indicating the respiratory condition of a subject (user) measured from the subject, acquires behavioral history information regarding the subject's behavioral history in a period prior to the measurement timing of the measurement data, inputs the data and the behavioral history information into a trained model (trained model 13), and obtains from the trained model a determination result as to whether or not the subject has symptoms of a respiratory disease.

[0009] (2) The information processing method according to (1), wherein the behavior history information includes at least one of medication history information related to a medication history and exercise history information related to an exercise history.

[0010] (3) The information processing method according to (2), wherein the medication history information includes the number of times medication was taken during the period.

[0011] (4) The information processing method according to (2) or (3), wherein the exercise history information includes information on the amount of exercise.

[0012] (5) The information processing method according to (2) or (3), wherein the exercise history information includes information on the frequency of exercise performed under a specific situation.

[0013] (6) An information processing device (information processing server 10) having a processor (processor 11) that performs processing to acquire data (processed measurement data) based on measurement data measured from the subject (user) indicating the respiratory condition of the subject, acquire behavioral history information regarding the subject's behavioral history in a period prior to the measurement timing of the measurement data, input the data and the behavioral history information into a trained model (trained model 13), and obtain a determination result of whether or not the subject has symptoms of a respiratory disease from the trained model.

[0014] (7) An information processing program that causes a processor (processor 11) to execute the following processes: acquiring data (measurement-processed data) based on measurement data indicating the respiratory status of the subject (user) measured from the subject; acquiring behavioral history information regarding the behavioral history of the subject in a period prior to the measurement timing of the measurement data; inputting the data and the behavioral history information into a trained model (trained model 13); and obtaining, from the trained model, a determination result as to whether or not the subject has symptoms of a respiratory disease.

[0015] (8) A method for generating a trained model in which a processor (processor 11) acquires, as training data, a plurality of pieces of data based on measurement data indicating the respiratory state of a first subject (monitor user) measured from the first subject, behavioral history information regarding the behavioral history of the first subject in a period prior to the measurement timing of the measurement data, and a doctor's judgment result regarding the occurrence or non-occurrence of symptoms of a respiratory disease in the first subject on a day including the measurement timing, and executes machine learning based on the plurality of pieces of training data into a program, thereby obtaining a trained model (trained model 13) that outputs a judgment result regarding the occurrence or non-occurrence of symptoms of a respiratory disease in the second subject when data (processed measurement data) based on measurement data indicating the respiratory state of the second subject measured from a second subject (user) and behavioral history information regarding the behavioral history of the second subject in a period prior to the measurement timing of the measurement data are input.

[0016] (9) A trained model (trained model 13) that has been machine-learned using as learning data data: data (processed measurement data) based on measurement data indicating the respiratory state of a first subject (monitor user) measured from the first subject; behavioral history information regarding the behavioral history of the first subject in a period prior to the measurement timing of the measurement data; and a doctor's judgment result regarding the occurrence or non-occurrence of symptoms of a respiratory disease in the first subject on a day including the measurement timing; wherein, when data (processed measurement data) based on measurement data indicating the respiratory state of a second subject (user) measured from the second subject and behavioral history information regarding the behavioral history of the second subject in a period prior to the measurement timing of the measurement data are input, the trained model (trained model 13) causes a processor (processor 11) to execute a process to output a judgment result regarding the occurrence or non-occurrence of symptoms of a respiratory disease in the second subject.

[0017] (10) A measuring device (measuring device 40) that measures measurement data indicating the respiratory condition of a subject from the subject, comprising: a communication unit capable of communicating with a terminal (user terminal 30) that can acquire behavioral history information regarding the subject's behavioral history for a period prior to the measurement timing of the measurement data; an output device; and a processor, wherein the processor transmits the measurement data to the terminal; inputs data based on the measurement data and the behavioral history information into a trained model; receives from the terminal a judgment result regarding the presence or absence of symptoms of a respiratory disease in the subject obtained from the trained model; and outputs the received judgment result from the output device.

[0018] According to the technology disclosed herein, it is possible to provide an information processing method, an information processing device, and an information processing program that can accurately determine the presence or absence of symptoms of respiratory disease, as well as a trained model used therein and a method for generating the same, and a measuring device.

[0019] FIG. 1 is a schematic diagram showing the general configuration of a symptom determination system 100. As shown in FIG.

[0020] (Outline of information processing method related to the technology of the present disclosure) In the information processing method, a processor acquires data based on measurement data indicating the respiratory condition of the subject measured from the subject, acquires behavioral history information (for example, at least one of medication history information related to medication history and exercise history information related to exercise history) regarding the subject's behavioral history for a period prior to the measurement timing of the measurement data, inputs the data and the behavioral history information into a trained model, and performs processing to obtain from the trained model a determination result as to whether or not the subject has symptoms of a respiratory disease.

[0021] In this way, by inputting not only data based on the measurement data measured from the subject but also behavioral history information based on the subject's past behavior into the trained model, the trained model can output a determination result on the presence or absence of symptoms of a respiratory disease in the subject. As a result, compared to a configuration such as a wheezing sensor that analyzes measurement data measured from the subject using a specific algorithm to determine the presence or absence of symptoms, it is possible to determine the presence or absence of symptoms taking the subject's past behavior into consideration, thereby improving the accuracy of the determination.

[0022] For example, consider a case where a subject is taking a medication prescribed by a doctor. When the subject uses a device to determine whether or not symptoms are present, if the medication has moderately improved the subject's airway condition, the device is expected to output a result indicating no symptoms. On the other hand, if the subject were to undergo a medical examination with the same condition, the doctor would likely make a more stringent assessment than the device, as the doctor would question the subject about the medication status and observe breathing sounds to determine the effectiveness of the medication. Therefore, the doctor's assessment may be more stringent than the device's assessment, so as not to miss even the slightest sign of symptoms. Thus, the criteria used for assessments by the device and by the doctor may differ depending on the subject's medication history. Furthermore, the subject's airway condition may change depending not only on the subject's medication history but also on their exercise history. For example, people who exercise frequently tend to experience reduced stress, which is expected to lead to improved airway conditions. However, even in this case, the doctor's assessment may differ from the device's assessment depending on the subject's exercise history.

[0023] The technology disclosed herein determines the presence or absence of symptoms using a trained model that has undergone machine learning using behavioral history information acquired from each of a large number of people (monitoring users, described below), data based on measurement data indicating respiratory status, and a doctor's diagnosis of the presence or absence of symptoms as training data. This makes it possible to determine the presence or absence of symptoms by taking into account not only data based on measurement data, which is conventionally used by devices, but also behavioral history (medication history, exercise history, etc.). As a result, the trained model can obtain results that are close to those obtained by a doctor, making it possible to accurately determine the presence or absence of symptoms of respiratory diseases.

[0024] An example of the configuration of a respiratory disease symptom determination system including an apparatus that executes an information processing method according to the technology of the present disclosure will be described below.

[0025] (System Configuration) Fig. 1 is a schematic diagram showing the overall configuration of a symptom determination system 100. The target users of the symptom determination system 100 are those who have been diagnosed with a respiratory disease by a doctor and have been prescribed a therapeutic drug, but users who have not been prescribed a therapeutic drug can also use the system. The symptom determination system 100 includes an information processing server 10, a user terminal 30 such as a smartphone carried by the user (subject), and a measuring device 40 carried by the user. The user terminal 30 and the information processing server 10 are connected to a network 20 such as the Internet and configured to be able to communicate with each other.

[0026] The measuring device 40 is a device for measuring measurement data indicating the user's respiratory state from the user, such as respiratory sound data (e.g., time-to-amplitude data) or lung capacity data (e.g., expiratory volume-to-flow data (flow-volume curve)).

[0027] The measuring device 40 may be, for example, a device that includes a sensor unit including a microphone and measures and records the user's respiratory sound data using the microphone while the sensor unit is placed against the user's chest. The measuring device 40 may also be a peak flow meter that measures and records the user's lung capacity data (flow-volume curve). The measuring device 40 and the user terminal 30 can be connected via wired or wireless communication, and the measurement data measured by the measuring device 40 is transmitted to the user terminal 30. Specifically, the measuring device 40 includes a sensor unit (a flow rate detection unit in the case of a peak flow meter), a communication unit that can communicate with the user terminal 30 via wired or wireless communication, an output device such as a display or speaker, and a device processor that controls these devices.

[0028] A management application capable of managing the user's behavior history is installed in the user terminal 30. The management application records, in a memory, medication history data indicating a medication history, which is one type of behavior history of the user, and exercise history data indicating an exercise history, which is one type of behavior history. The management application records the user's medication history data and exercise history data by utilizing the location detection function, activity amount detection function, various information input function, and various information acquisition function from an external server via the network 20, which are installed in the user terminal 30.

[0029] When a user takes a medication prescribed by a doctor, the user operates the management app to input the date and time the medication was taken. The management app then records this input information in memory as medication history data.

[0030] When a user exercises while carrying the user terminal 30 or wearing a smart watch or the like connectable to the user terminal 30, the management app acquires the user's exercise history data and records it in memory. The user's exercise history data includes, for example, the intensity of the exercise (unit: METs), the duration of the exercise, the location of the exercise (indoor or outdoor), and the environment of the location of the exercise (temperature, allergen amount, etc.). The location and environment indicate the circumstances under which the exercise is performed. The user's exercise history data may also include activity levels such as the number of steps taken or calories burned per unit period (e.g., one day). The amount of allergens is defined, for example, by the amount of pollen dispersed or PM2.5.

[0031] The intensity of the exercise, the number of steps, the calories burned, etc. can be acquired by the activity amount detection function of the user terminal 30 or a smart watch. The location where the exercise was performed can be acquired by the location detection function of the user terminal 30 or a smart watch. The environment of the location where the exercise was performed can be acquired by the various information acquisition function of the user terminal 30.

[0032] The information processing server 10 includes a processor 11 and a storage unit 12. The storage unit 12 includes a work memory such as a RAM (Random Access Memory) and a non-transitory storage medium such as a hard disk or a flash memory. The storage unit 12 stores an information processing program for the processor 11 of the information processing server 10 to execute an information processing method.

[0033] The processor 11 may be a CPU (Central Processing Unit), which is a general-purpose processor that executes software (programs) and performs various functions, a programmable logic device (PLD), which is a processor whose circuit configuration can be changed after manufacture, such as an FPGA (Field Programmable Gate Array), or a dedicated electrical circuit, which is a processor having a circuit configuration designed exclusively for executing specific processing, such as an ASIC (Application Specific Integrated Circuit). The processor 11 may be composed of a single processor, or may be composed of a combination of two or more processors of the same or different types (for example, multiple FPGAs, or a combination of a CPU and an FPGA). More specifically, the hardware structure of the processor 11 is an electric circuit (circuitry) that combines circuit elements such as semiconductor elements. When the processor 11 is made up of multiple processors, the multiple processors do not need to be installed in the same device, but may be installed in multiple devices that are distributed over the network 20.

[0034] The memory unit 12 stores a trained model 13. The trained model 13 is generated by causing a training model configured by a program to perform machine learning using teacher data (training data). The trained model 13 may be generated by the processor 11 of the information processing server 10, or may be generated by a processor of a computer other than the information processing server 10. In the following, a method for generating the trained model 13 will be described, assuming that the processor 11 generates the trained model 13.

[0035] (Method for generating a trained model) The processor 11 acquires a sample data group from the storage unit 12. Each sample data included in this sample data group includes medication history data and exercise history data (hereinafter referred to as first data) recorded by a monitor user other than the user using the symptom determination system 100 using the same terminal as the user terminal 30 over a predetermined period (e.g., one week, two weeks, one month, etc.). Each sample data also includes measurement data (hereinafter referred to as second data) obtained by the monitor user measuring respiratory status using the same device as the measuring device 40 after the end of the predetermined period (e.g., the day following the end of the predetermined period). Each sample data also includes a doctor's assessment of the presence or absence of symptoms of a respiratory disease when the monitor user is examined by the doctor on a day including the time when the measurement data was measured (hereinafter referred to as third data). In this way, sample data including the first data, second data, and third data is generated for each of a large number of monitor users and stored in the storage unit 12 as a sample data group.

[0036] The processor 11 generates medication history information regarding the medication history of the monitor user during a predetermined period, based on the first data in each sample data of the sample data group acquired from the storage unit 12. The medication history information is information obtained by processing the medication history data, and is, for example, the number of times a medication was taken during a predetermined period (i.e., medication frequency), or the number of times a medication was taken for each divided period when the predetermined period is divided into multiple periods (information indicating the distribution of timing at which medication was taken during a predetermined period).

[0037] The processor 11 also generates exercise history information about the monitor user's exercise history during a predetermined period based on the first data in each sample data of the sample data group acquired from the storage unit 12. The exercise history information is information obtained by processing the exercise history data, and includes, for example, first information about the amount of exercise performed during the predetermined period, or second information about the frequency of exercise performed under specific circumstances during the predetermined period. The exercise history information may be composed of a combination of the first information and the second information.

[0038] The first information may be, for example, the amount (METs-hours) of physical activity at or above a predetermined intensity (e.g., 3 METs). For example, if exercise at an intensity of 3 METs is performed for one hour and exercise at an intensity of 5 METs is performed for one hour during a predetermined period, (3 METs x 1 hour) + (5 METs x 1 hour) = 8 [METs-hours] is generated as the first information on the amount of exercise. The number of times or the amount of time that physical activity at or above a predetermined intensity is performed during the predetermined period may also be generated as the first information on the amount of exercise. Furthermore, the cumulative number of steps or cumulative calories burned during the predetermined period may also be generated as the first information on the amount of exercise.

[0039] As the second information, for example, indoor exercise information indicating the number of times or the duration of exercise at or above a predetermined intensity performed indoors during a predetermined period, and outdoor exercise information indicating the number of times or the duration of exercise at or above a predetermined intensity performed outdoors during a predetermined period are generated.

[0040] The outdoor exercise information may be further subdivided. For example, the outdoor exercise information may be generated by dividing it into first outdoor exercise information indicating the number of times or the duration of exercise performed at a predetermined intensity or above with an allergen amount at or above a predetermined level, and second outdoor exercise information indicating the number of times or the duration of exercise performed at a predetermined intensity or above with an allergen amount below the predetermined level.

[0041] In addition to or instead of the first outdoor exercise information and the second outdoor exercise information, third outdoor exercise information indicating the number of times or the duration of exercise at or above a predetermined intensity when the temperature is above a predetermined level, and fourth outdoor exercise information indicating the number of times or the duration of exercise at or above a predetermined intensity when the temperature is below the predetermined level may be generated. Indoors, outdoors, outdoors with an allergen amount above a predetermined level, outdoors with an allergen amount below a predetermined level, outdoors with a temperature above a predetermined level, and outdoors with a temperature below a predetermined level each constitute a specific situation.

[0042] Furthermore, based on the second data (measurement data) in each sample data of the sample data group acquired from the memory unit 12, the processor 11 generates measured processed data by processing this second data into a format suitable for learning.

[0043] The processed measurement data is a feature value extracted from the measurement data (breath sound data or lung capacity data). The feature value can be appropriately selected to show a significant difference between people with and without respiratory disease.

[0044] When the measurement data is respiratory sound data, for example, the processor 11 generates frequency versus amplitude data from the respiratory sound data (time versus amplitude data), selects a plurality of predetermined frequencies from this data (frequencies at which the difference in amplitude between people with and without respiratory disease is particularly large), and obtains the amplitude values ​​corresponding to each frequency as measurement processed data.

[0045] Alternatively, the processor 11 may process the respiratory sound data to generate frequency versus sound pressure data, and obtain the ratio of the peak value of sound pressure in this data to the width between the frequencies corresponding to the minimum values ​​of sound pressure on either side of the peak value as the measured processed data.

[0046] Alternatively, the processor 11 may process the respiratory sound data to generate three-dimensional data of frequency, sound pressure, and time, and select from the three-dimensional data the frequency during which the sound pressure reaches a maximum value as the measured and processed data. Alternatively, the processor 11 may obtain, as the measured and processed data, feature values ​​that can be extracted directly from the respiratory sound data (e.g., the number of times the amplitude reaches a certain level and the time for which the amplitude reaches a certain level) without frequency analysis of the respiratory sound data.

[0047] It is known that the shape of vital capacity data (flow-volume curves) measured by a peak flow meter differs between people with and without respiratory disease. Therefore, when the measurement data is vital capacity data, the processor 11 extracts a flow amount that can identify the difference in shape from the flow-volume curve as vital capacity data (for example, a flow amount corresponding to 50% or 25% of the maximum exhalation volume), and obtains this flow amount as measurement processed data.

[0048] Alternatively, the processor 11 may extract flow volumes corresponding to multiple ratios (e.g., 90%, 80%, 70%, etc.) of the maximum exhaled volume from the flow-volume curve and use these as the measured processed data.

[0049] Alternatively, the processor 11 may generate data from the vital capacity data, with absolute displacement on the horizontal axis and flow volume on the vertical axis. It is known that the position of the center of gravity of absolute displacement differs between people with and without respiratory disease. Therefore, the processor 11 may identify the center of gravity of absolute displacement from the data of absolute displacement versus flow volume, and use this center of gravity as the measured and processed data.

[0050] The processor 11 uses the data set of the medication history information, exercise history information, and processed measurement data corresponding to the monitored user generated as described above, and the third data (a doctor's determination of the presence or absence of symptoms) corresponding to the monitored user as training data, and causes the learning model to perform machine learning based on multiple data sets corresponding to multiple monitored users, thereby generating a trained model 13. The medication history information and exercise history information each constitute behavioral history information related to behavioral history.

[0051] The trained model 13 has learned various parameters so that, when medication history information and exercise history information for a predetermined period and processed measurement data generated based on measurement data measured by the user after the predetermined period are input, the trained model 13 outputs a determination result of whether or not the user has symptoms of a respiratory disease. The machine learning method is not particularly limited, and any method such as logistic regression, decision tree, random forest, gradient boosting decision tree, or neural network can be used.

[0052] (Use of trained model) First, the user connects the user terminal 30 and the measuring device 40 and measures measurement data using the measuring device 40. The measurement data measured by the measuring device 40 and its measurement date and time information are transmitted from the measuring device 40 to the user terminal 30 and acquired by the management app of the user terminal 30. Upon acquiring the measurement data, the management app reads from memory the medication history data and exercise history data recorded for the past period from the measurement date and time (measurement timing) of the measurement data up to the above-mentioned predetermined period, and transmits them together with the measurement data to the information processing server 10.

[0053] When the processor 11 acquires the medication history data, exercise history data, and measurement data transmitted from the user terminal 30, it generates medication history information based on the medication history data, generates exercise history information based on the exercise history data, and generates processed measurement data based on the measurement data.

[0054] Next, the processor 11 inputs the generated medication history information, exercise history information, and processed measurement data into the trained model 13, and obtains the determination result of the presence or absence of symptoms of a respiratory disease as an output of the trained model 13. Upon obtaining this determination result, the processor 11 transmits this determination result to the management app of the user terminal 30. The management app performs processing to display the received determination result on the display device of the user terminal 30 or output the result as audio from the speaker. This allows the user to know the presence or absence of symptoms. Alternatively, the management app transmits the received determination result to the measuring device 40. Upon receiving the determination result, the device processor of the measuring device 40 outputs the determination result from an output device. This may output the determination result from the display or speaker of the measuring device 40. By having the measuring device 40 perform everything from measurement to result output, the value of the measuring device 40 can be increased.

[0055] (Variant example of trained model) The trained model 13 is obtained by machine learning using data sets of medication history information, exercise history information, measurement and processing data, and third data (a doctor's assessment results) as training data, but is not limited to this.

[0056] For example, the trained model 13 may be obtained by machine learning using a data set of either the medication history information or the exercise history information, the processed measurement data, and the third data (the doctor's assessment results) as training data. In this case, the processor 11 inputs either the medication history information or the exercise history information of the user and the processed measurement data into the trained model 13, and obtains a diagnosis result of the presence or absence of symptoms from the trained model 13.

[0057] The trained model 13 may be machine-learned to input at least one of medication history information, exercise history information, information on the user's sleep history (e.g., the number of hours of sleep per day during a period or the average sleep score during that period), information on the user's drinking history (e.g., the amount of alcohol consumed per day during that period or the number of drinks consumed during that period), information on the user's smoking history (e.g., the number of cigarettes smoked per day during that period or the number of cigarettes smoked during that period), or information on the user's bathing history (e.g., the number of bathing hours per day during that period or the number of baths consumed during that period), together with the measured and processed data, and output a determination result on the presence or absence of symptoms of a respiratory disease. The sleep history, drinking history, smoking history, and bathing history are all part of the user's behavioral history.

[0058] The above-mentioned dataset may further include user information to perform machine learning.

[0059] User information refers to information about the attributes (gender, age, physique (BMI), nationality, etc.) of the monitor user who is the measurement source of the measurement data included in the sample data. Based on each sample data in the sample data group, the processor 11 generates, for example, medication history information, exercise history information, and processed measurement data, and uses these, along with the user information and the third data, as training data. The processor 11 then executes machine learning on the learning program based on this training data to generate a trained model 13. This allows the generation of a trained model 13 that outputs a determination result of whether or not a user has symptoms of a respiratory disease when medication history information, exercise history information, processed measurement data, and user information about the user are input. In this way, by further utilizing the user information, the presence or absence of the user's symptoms can be determined with higher accuracy.

[0060] In the above description, the processor 11 generates the medication history information, exercise history information, and processed measurement data, but this is not limited to this. For example, a terminal-side processor executing a management app on the user terminal 30 may generate the medication history information, exercise history information, and processed measurement data and transmit the generated medication history information, exercise history information, and processed measurement data to the information processing server 10, thereby allowing the processor 11 to acquire the medication history information, exercise history information, and processed measurement data. Furthermore, when the terminal-side processor generates the medication history information, exercise history information, and processed measurement data, the trained model 13 may be incorporated into the management app. In this case, the terminal-side processor inputs the medication history information, exercise history information, and processed measurement data into the trained model 13 to obtain a determination result of the presence or absence of symptoms.

[0061] Although various embodiments have been described above, it goes without saying that the present invention is not limited to such examples. It is clear that a person skilled in the art can conceive of various modifications or alterations within the scope of the claims, and it is understood that these also naturally fall within the technical scope of the present invention. Furthermore, the components of the above embodiments may be combined in any manner as long as they do not deviate from the spirit of the invention.

[0062] This application is based on a Japanese patent application (Patent Application No. 2023-218152) filed on December 25, 2023, the contents of which are incorporated herein by reference.

[0063] REFERENCE SIGNS LIST 10 Information processing server 11 Processor 12 Storage unit 13 Model 20 Network 30 User terminal 40 Measuring device 100 Symptom determination system

Claims

1. An information processing method, wherein a processor obtains data based on measurement data indicating the respiratory state of a subject measured from the subject, obtains behavior history information regarding the behavior history of the subject in a period past the measurement timing of the measurement data, and inputs the data and the behavior history information into a learned model to obtain a determination result on the presence or absence of symptoms of a respiratory disease of the subject from the learned model.

2. The information processing method according to claim 1, wherein the behavior history information includes at least one of medication history information regarding a medication history and exercise history information regarding an exercise history.

3. The information processing method according to claim 2, wherein the medication history information includes the number of times of taking medication in the period.

4. The information processing method according to claim 2 or 3, wherein the exercise history information includes information on the amount of exercise.

5. The information processing method according to claim 2 or 3, wherein the exercise history information includes information on the frequency of exercise performed under specific circumstances.

6. An information processing apparatus comprising a processor that obtains data based on measurement data indicating the respiratory state of a subject measured from the subject, obtains behavior history information regarding the behavior history of the subject in a period past the measurement timing of the measurement data, and inputs the data and the behavior history information into a learned model to obtain a determination result on the presence or absence of symptoms of a respiratory disease of the subject from the learned model.

7. An information processing program that causes a processor to execute a process of obtaining data based on measurement data indicating the respiratory state of a subject measured from the subject, obtaining behavior history information regarding the behavior history of the subject in a period past the measurement timing of the measurement data, and inputting the data and the behavior history information into a learned model to obtain a determination result on the presence or absence of occurrence of symptoms of a respiratory disease of the subject from the learned model.

8. The processor acquires a plurality of pieces of learning data including data based on measurement data indicating the respiratory state of the first subject measured from the first subject, behavior history information regarding the behavior history of the first subject in a period prior to the measurement timing of the measurement data, and a determination result by a doctor on whether or not symptoms of a respiratory disease of the first subject occurred on the day including the measurement timing. Then, the processor executes machine learning based on the plurality of pieces of learning data in a program, and when data based on measurement data indicating the respiratory state of the second subject measured from the second subject and behavior history information regarding the behavior history of the second subject in a period prior to the measurement timing of the measurement data are input, a learned model that outputs a determination result on whether or not symptoms of a respiratory disease of the second subject occurred is obtained. A method for generating a learned model.

9. A learned model obtained by performing machine learning using, as learning data, data based on measurement data indicating the respiratory state of the first subject measured from the first subject, behavior history information regarding the behavior history of the first subject in a period prior to the measurement timing of the measurement data, and a determination result by a doctor on whether or not symptoms of a respiratory disease of the first subject occurred on the day including the measurement timing. When data based on measurement data indicating the respiratory state of the second subject measured from the second subject and behavior history information regarding the behavior history of the second subject in a period prior to the measurement timing of the measurement data are input, the processor is caused to execute a process of outputting a determination result on whether or not symptoms of a respiratory disease of the second subject occurred. A learned model.

10. A measuring device that measures measurement data indicating the respiratory state of a subject from the subject, the measuring device including: a communication unit capable of communicating with a terminal capable of acquiring behavior history information regarding the behavior history of the subject in a period prior to the measurement timing of the measurement data; an output device; and a processor. The processor transmits the measurement data to the terminal, inputs data based on the measurement data and the behavior history information into a learned model, receives from the terminal a determination result on whether or not symptoms of a respiratory disease of the subject are present obtained from the learned model, and causes the received determination result to be output from the output device. A measuring device.

Images